I am a Ph.D. student at Princeton University, advised by Karthik Narasimhan. Previously, I graduated from Yao Class at Tsinghua University.

In my work, I build language agents (e.g. CALM, WebShop, ReAct, Reflexion, ToT) to interact with internal and external worlds, via reasoning and acting.

In my life, I like reading, basketball, pool, travel, and rap.

I would appreciate (annoynomous) feedback about anything!

Recent News

• May 2023: There has been a malicious, non-runnable, probably ChatGPT-generated ToT repo that has more stars than the official ToT repo. I have explained the situation here. Please de-star the malicious repo and star the official repo to prevent other people from be misled and wasting time, thanks!

• Apr 2023: I attended LangChain Agent Webinar (long YouTube video and short Twitter summary).

Recent Papers

• Referral Augmentation for Zero-Shot Information Retrieval
  Michael Tang, Shunyu Yao, John Yang, Karthik Narasimhan
  paper | code | tweet

• Reflexion: Language Agents with Verbal Reinforcement Learning
  Noah Shinn, Federico Cassano, Beck Labash, Ashwin Gopinath, Karthik Narasimhan, Shunyu Yao
  paper | code | tweet

• Tree of Thoughts: Deliberate Problem Solving with Large Language Models
  Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, Karthik Narasimhan
  paper | code | tweet

• ReAct: Synergizing Reasoning and Acting in Language Models
  Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, Yuan Cao
  ICLR 2023 (Oral top 5%)
  paper | code | tweet | project | Google AI blogpost

• WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
  Shunyu Yao*, Howard Chen*, John Yang, Karthik Narasimhan
  NeurIPS 2022
  paper | code | tweet | project | demo | Quanta Magazine

Recent Talks

• Towards Autonomous Language Agents
  • DeepMind, London, Apr 2023
  • EPFL NLP Group, Lausanne, Mar 2023
  • Berekley NLP Group, Berekley, Mar 2023
  • OpenAI, San Francisco, Mar 2023
  • Adept AI, San Francisco, Mar 2023
• Re-thinking Reinforcement Learning in the Era of Large Language Models
  • Jane Street, New York, Apr 2023
• ReAct: Synergizing Reasoning and Acting in Language Models
  • ICLR, Kigali, May 2023
  • EMNLP EvoNLP & NILLI Workshops, Abu Dhabi, Dec 2022
  • NeurIPS FMDM Workshop, New Orleans, Nov 2022
• Towards Human-like Language Models
  • Princeton Cognitive Science Colloquium, Princeton, Nov 2022
• WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
  • University of Washington, Seattle, July 2022

Recent Readings

• 西方语言学史 （姚小平）
• Antoni Gaudí（dosde）
• A Simpler Life (The School of Life)
• The Search (John Battelle)
• Leadership: In Turbulent Times (Doris Kearns Goodwin)

(last updated: May 2023)